5D Library › Relationship Rupture Survival Analysis, No-Contact Memory Decay and Reconciliation Game Windows · 中文

Chapter 8. Practice: Three Ways to Spend the Year, Measuring Oneself, and Too Few Cases

Three ways to spend the year

p14 compares three ways for the person who wants to reunite to spend the year after a rupture. Reconciling is given a value of 10, every day spent waiting and hoping costs 0.01, and the other person moves on with a mean time of 120 days.

Calculation

# Chapter 8. p14: Three ways to spend the year after a rupture, valued
# for the person who wants to reconcile. Reconciling is worth 10;
# every day spent waiting and hoping costs 0.01 (a life on hold); the
# other person moves on with hazard 1 / 120 a day. Welcome chances come
# from the p05 model.
#   A: no contact; let go on day 0 (value 0).
#   B: one calm message on the best day of p06 (day 29); stop if not
#      welcomed.
#   C: contact 3 times a week in days 0 to 30, then one message on day
#      60 (the p05 chance), still waiting until then.
from math import exp

def welcome(d, extra=0.0):
    n, p = 1.5 * exp(-d / 17.5), exp(-d / 75)
    return 1 / (1 + exp(-6 * (p - n - extra) + 1))

if __name__ == "__main__":
    b = welcome(29) * exp(-29 / 120) * 10 - 0.01 * 29
    c = 0.017 * exp(-60 / 120) * 10 - 0.01 * 60
    print("   A  let go on day 0           value {:+.3f}".format(0.0))
    print("   B  one message on day 29      value {:+.3f}".format(b))
    print("   C  pursue, then ask day 60    value {:+.3f}".format(c))
    for cost in (0.02, 0.05):
        v = welcome(29) * exp(-29 / 120) * 10 - cost * 29
        print("   B with waiting cost {:.2f} a day: {:+.3f}".format(cost, v))
#    A  let go on day 0           value +0.000
#    B  one message on day 29      value +5.959
#    C  pursue, then ask day 60    value -0.497
#    B with waiting cost 0.02 a day: +5.669
#    B with waiting cost 0.05 a day: +4.799

Letting go at once is worth 0 by construction. Sending one calm message on day 29, and stopping if it is not welcome, is worth +5.959 in the model; pursuing with three contacts a week in the first month and asking on day 60 is worth -0.497, worse than letting go. If waiting costs more, 0.02 or 0.05 a day, the single message is still worth +5.669 or +4.799. The comparison depends on the value of 10, which is the person’s own and may be much lower once they think about the relationship calmly; but the ordering of the second and third policies does not depend on it. One respectful attempt dominates pursuit.

Can a person measure their own time constants?

The models of Chapters 2 and 3 use time constants that differ between people. p15 asks whether someone could estimate their own from twelve weekly ratings of how angry they feel and how fondly they remember.

Calculation

# Chapter 8. p15: Can a person measure their own time constants? Twelve
# weekly self-ratings of anger N follow N = 1.5 exp(-t / 17.5) with
# rating noise (sd 0.15, ratings rounded to the nearest 0.1 and floored
# at 0.05). Fit log N against t by least squares; tn = -1 / slope.
# Repeat 2,000 times. Then the same for a slow memory P with tp = 75
# observed for only 12 weeks. Seed 92.
import random
from math import exp, log

def fit(rng, a, tau, sd=0.15):
    xs, ys = [], []
    for w in range(1, 13):
        t = 7 * w
        y = a * exp(-t / tau) + rng.gauss(0, sd)
        y = max(0.05, round(y, 1))
        xs.append(t)
        ys.append(log(y))
    mx, my = sum(xs) / 12, sum(ys) / 12
    b = sum((x - mx) * (y - my) for x, y in zip(xs, ys)) / \
        sum((x - mx) ** 2 for x in xs)
    return -1 / b if b < 0 else float("inf")

if __name__ == "__main__":
    rng = random.Random(92)
    for lab, a, tau in (("tn", 1.5, 17.5), ("tp", 1.0, 75.0)):
        est = sorted(fit(rng, a, tau) for _ in range(2000))
        q = lambda p: est[int(p * (len(est) - 1))]
        print("   true {} {:5.1f}: median fit {:6.1f}; 10% {:6.1f};"
              " 90% {:6.1f}".format(lab, tau, q(0.5), q(0.1), q(0.9)))
#    true tn  17.5: median fit   29.4; 10%   24.7; 90%   39.3
#    true tp  75.0: median fit   70.9; 10%   47.3; 90%  110.8

For anger with a true time constant of 17.5 days, the fitted value has a median of 29.4 and runs from 24.7 to 39.3: the estimate is too high, because after five or six weeks the ratings sit at the bottom of the scale and stop carrying information. For the slow positive memory with a true value of 75 days, the median fit is 70.9, but the range runs from 47.3 to 110.8. Twelve weeks of self-ratings are not enough to know one’s own numbers precisely; they are enough to see that the two processes run at different speeds.

How much can a few break-ups teach?

Calculation

# Chapter 8. p16: How much can a few break-ups teach one person? With a
# uniform prior on the chance r that a reunion of theirs lasts a year,
# k lasting reunions out of n give a Beta(k + 1, n - k + 1) posterior.
# Its 90% interval is found by simulation (40,000 draws, seed 92).
import random

def interval(rng, k, n, m=40000):
    xs = sorted(rng.betavariate(k + 1, n - k + 1) for _ in range(m))
    return xs[int(0.05 * m)], xs[int(0.5 * m)], xs[int(0.95 * m)]

if __name__ == "__main__":
    rng = random.Random(92)
    print("   lasting / reunions   5%      median   95%")
    for k, n in ((0, 1), (1, 3), (2, 3), (5, 15), (50, 150)):
        lo, md, hi = interval(rng, k, n)
        print("   {:>8} / {:<8}   {:.3f}   {:.3f}    {:.3f}".format(
            k, n, lo, md, hi))
#    lasting / reunions   5%      median   95%
#           0 / 1          0.026   0.293    0.779
#           1 / 3          0.097   0.385    0.755
#           2 / 3          0.249   0.614    0.903
#           5 / 15         0.176   0.347    0.549
#          50 / 150        0.274   0.335    0.399

With a uniform prior, one reunion that did not last leaves the chance that a reunion of this person’s lasts a year anywhere between 0.026 and 0.779 (90%). One lasting reunion out of three leaves it between 0.097 and 0.755; five out of fifteen narrows it to 0.176 to 0.549, and only fifty out of a hundred and fifty, a number no one has, would pin it to between 0.274 and 0.399. A person’s own history is too short to estimate their chances; what it can show is the pattern of Chapter 5, whether the cause of each rupture recurred.

Disclosure

Statement: this book is about the mathematics of rupture, memory, signalling and reunion. It is not psychological counselling, therapy or relationship advice, and its parameters are illustrative. Anyone in distress after a break-up, or in a relationship with violence, threats or coercion, should seek help from a qualified professional or local support services. Contacting someone who has asked not to be contacted is not covered by any model in this book.

Note

Pre-registered tests: the hypotheses of Chapter 2 on the two speeds of fading and of Chapter 3 on the cost of early unwanted contact should each be registered, with measures, sample and analysis, before data are collected, and the results published whether positive or negative. Any such study needs ethics approval and must not ask participants to contact former partners.

Summary

In the model, one calm message after the anger has faded is worth far more than pursuit, and pursuit is worth less than letting go. People cannot measure their own time constants precisely from a few weeks of ratings, nor their own chances from a few relationships. The most reliable guide is the cause of the rupture and whether it has changed, and the other person’s answer.

Fan, Y. (2026). Relationship Rupture Survival Analysis, No-Contact Memory Decay and Reconciliation Game Windows: Negative-Affect Dissipation Rates, Dual-Process Nostalgia Peaks and Signaling Equilibria [关系断裂生存分析、断联期记忆衰减与复联博弈窗口] (Version 1.0.0). 5D Library. https://doi.org/10.5281/zenodo.24090241 · Licensed under Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0).